基于用户兴趣度的PageRank改进算法  

Improved PageRank Algorithm Based on User Interest Degree

作　　者：黄贤英[1] 陈红阳[1] 

机构地区：[1]重庆理工大学计算机科学与工程学院,重庆400054

出　　处：《重庆理工大学学报（自然科学）》2014年第5期74-78,共5页Journal of Chongqing University of Technology：Natural Science

基　　金：国家自然科学基金项目(61173184);重庆市教委科技计划项目(KJ100821);重庆理工大学研究生创新基金项目(YCX2012317)

摘　　要：传统的PageRank算法容易导致主题漂移、偏重旧网页、用户对搜索结果的主观选择被忽略等问题。针对PageRank算法存在的上述缺陷,提出了一种基于用户兴趣度的网页排序算法——PRUI算法。该算法主要从网页自身的客观特性和用户兴趣的主观特性两方面对网页的PR值进行重新估算,并依据估算后的网页PR值对网页做重排序。相比传统的PageRank算法,改进的PRUI算法进一步提高了系统检索的准确率和首页命中率。Traditional PageRank algorithm had such drawbacks as theme drifting, history pages being emphasized and the user＇s interests in results being ignored. Facing the above defects described, an improved ranking algorithm called PRUI was proposed, which was based on user interest degree. It mainly re-estimated PR value of web page integrating objective characteristics of web page with sub- jective characteristics of user~ interests, and ranked the web page according to the calculated PR val- ue again. The experimental results show that PRUI algorithm has acquired higher retrieval accuracy as well as first page hit ratio, compared with traditional PageRank algorithm.

关 键 词：搜索引擎 PAGERANK算法 主题漂移 用户兴趣度 页面排序 

分 类 号：TP391.03[自动化与计算机技术—计算机应用技术]